kanban-stuck-task-recovery

kanban-stuck-task-recovery is a skill for Claude Code, Codex from humanerd-drew/opencode-drewgent. It costs 0 tokens per session (1,141 once invoked), scanned A, original, MIT.

A procedure for diagnosing and recovering kanban tasks that remain marked as in progress even though their worker has stopped. A kanban board is a task list organized by work status.

In plain words
What is it for?
Use it to check worker processes and claim times, identify stuck tasks, and reset them after failures or outages.
Why use it?
It helps explain why a task is stuck, such as a dead worker, an expired claim, or a failed dispatcher, and prepares it to resume.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to check worker processes and claim times, identify stuck tasks, and reset them after failures or outages.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/humanerd-drew/opencode-drewgent/kanban-stuck-task-recovery
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add humanerd-drew/opencode-drewgent --skill kanban-stuck-task-recovery
Clone the repo
git clone --depth 1 https://github.com/humanerd-drew/opencode-drewgent

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for kanban-stuck-task-recovery

README.md
[![agentmods](https://agentmods.dev/badge/skills/humanerd-drew/opencode-drewgent/kanban-stuck-task-recovery/github.svg)](https://agentmods.dev/skills/humanerd-drew/opencode-drewgent/kanban-stuck-task-recovery)
Your own site
<a href="https://agentmods.dev/skills/humanerd-drew/opencode-drewgent/kanban-stuck-task-recovery"><img src="https://agentmods.dev/badge/skills/humanerd-drew/opencode-drewgent/kanban-stuck-task-recovery/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for kanban-stuck-task-recovery

Your own site · 80×15
<a href="https://agentmods.dev/skills/humanerd-drew/opencode-drewgent/kanban-stuck-task-recovery"><img src="https://agentmods.dev/badge/skills/humanerd-drew/opencode-drewgent/kanban-stuck-task-recovery.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,141 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.01141
Opus 5 $0.00000 $0.00571
Sonnet 5 $0.00000 $0.00228
Haiku 4.5 $0.00000 $0.00114

Measured 9d ago against content hash 9b0cc4a3857f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

kanban-stuck-task-recovery scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/brain/kanban-stuck-task-recovery/SKILL.md · 131 lines

How it starts

The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.


name: kanban-stuck-task-recovery description: Diagnose and recover stuck kanban in_progress tasks (worker dead, claim_expires expired, dispatcher down). Includes SQL reset script, root cause analysis, and preventive monitoring. type: skill space: outcome tags: [skill, kanban, operations] created: 2026-05-31 updated: 2026-05-31 links:

  • "[[@memory/kanban/KANBAN_INDEX]]"
  • "[[@memory/growth/kanban-maintenance-guide]]"
  • "[[@identity/brain/rules]]"---

Kanban Stuck Task Diagnosis & Recovery

When to Use

  • task_list(status='in_progress') returns tasks with no worker running
  • Worker processes (PID) are dead but tasks remain stuck in in_progress
  • claim_expires timestamps are past the current time
  • After a dispatcher outage, tasks need to be reset before the system resumes

Diagnosis

# 1. Find all in_progress tasks with their worker status
python3 -c "
import sqlite3
db = '~/.{{AGENT_NAME_LOWER}}/P2-hippocampus/kanban/state/{{AGENT_NAME_LOWER}}_tasks.db'
conn = sqlite3.connect(db)
cur = conn.cursor()
for id_, title, board, pid, expires in cur.execute(
    'SELECT id, title, board, worker_pid, claim_expires FROM tasks WHERE status=\"in_progress\"'
):
    print(f'{id_} | board={board} | pid={pid} | expires={expires}')
conn.close()
"

# 2. Check if worker PIDs are alive
ps -p 68898 -o pid,etime 2>/dev/null || echo "worker PID 68898 is DEAD"

Recovery Script

# Reclaim all stale in_progress tasks (expired claim_expires)
python3 -c "
import sqlite3
from datetime import datetime, timezone

db = '~/.{{AGENT_NAME_LOWER}}/P2-hippocampus/kanban/state/{{AGENT_NAME_LOWER}}_tasks.db'
conn = sqlite3.connect(db)
cur = conn.cursor()

stale = cur.execute('''
    SELECT id, title, worker_pid, claim_expires
    FROM tasks
    WHERE status='in_progress'
    AND (worker_pid IS NULL OR claim_expires < datetime('now'))
''').fetchall()

print(f'Found {len(stale)} stale in_progress tasks')
reclaimed = 0
for row in stale:
    tid = row[0]
    cur.execute('''
        UPDATE tasks
        SET status='ready', worker_pid=NULL, claim_expires=NULL, started_at=NULL
        WHERE id=? AND status='in_progress'
    ''', (tid,))
    if cur.rowcount > 0:
        print(f'RECLAIMED: {tid}')
        reclaimed += 1

conn.commit()
print(f'Total reclaimed: {reclaimed}')
conn.close()
"

Read the full file on GitHub · 131 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 131 lines · 0 tokens per session scan A 9b0cc4a3857f

Subscribe to this mod's changes

kanban-stuck-task-recovery is a skill published in the GitHub repository humanerd-drew/opencode-drewgent (2 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,141 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories